© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 62743
    Prev
    Next
    INDEX
    Explanations

    proper nouns, names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    åĨħå¤ĸ
    -0.27
    .original
    -0.26
    æŁ¯
    -0.26
    soever
    -0.26
    åĿļ
    -0.25
    伺
    -0.24
     april
    -0.24
    ducible
    -0.24
    对æĪij
    -0.24
    åı°
    -0.24
    POSITIVE LOGITS
    anst
    0.33
    骤
    0.27
    atre
    0.27
    è¨ĢãģĪãģ°
    0.26
    åľ°ä¸Ń
    0.26
    <tbody
    0.26
    åĬĽè¿ĺæĺ¯
    0.26
    esson
    0.25
    éĢļçŁ¥
    0.25
    eft
    0.24
    Activations Density 0.670%

    No Known Activations